A method to control a velocity of a vehicle includes: extracting an end point of a road region from an input image; measuring a visibility distance between an end point location corresponding to the end point and a location of a vehicle; and controlling the velocity of the vehicle based on the measured visibility distance.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A method to control a velocity of a vehicle, the method comprising: acquiring a first image of a road on which the vehicle travels using a first camera of the vehicle; acquiring a second image of the road on which the vehicle travels using a second camera of the vehicle; determining, from the first image, a first road region of the road on which the vehicle is traveling; determining, from the second image, a second road region of the road on which the vehicle is traveling; extracting a plurality of first end points of the first road region from the first image; extracting a plurality of second end points of the second road region from the second image; determining a plurality of pixel disparities between the plurality of first end points and the plurality of second end points; measuring a visibility distance between a position on the road corresponding to the plurality of first end points and the plurality of second end points, and a location of the vehicle, based on the plurality of pixel disparities; and controlling the velocity of the vehicle based on the visibility distance.
2. The method of claim 1 , wherein the extracting of the plurality of first end points and the plurality of second end points comprises: identifying lane lines from the first image and the second image, extracting a driving lane region from the first road region and the second road region based on the lane lines, and extracting, as the plurality of first end points and the plurality of second end points, end points of the driving lane region.
3. The method of claim 1 , wherein the extracting of the plurality of first end points and the plurality of second end points comprises: extracting, as the plurality of first end points and the plurality of second end points, pixels at farthest distances from a side of the vehicle in the first image and the second image, among pixels included in the first road region and the second road region.
4. The method of claim 1 , wherein the extracting of the plurality of first end points and the plurality of second end points comprises: identifying a center line on the first road region and the second road region from the first image and the second image; and extracting, as the plurality of first end points and the plurality of second end points, pixels at farthest distances from a side of the vehicle in the first image and the second image, among pixels included in the center line.
5. The method of claim 1 , wherein the determining of the plurality of pixel disparities comprises: extracting a pixel disparity map from the first image and the second image using a pixel disparity model that is trained to output a training display map from a training image, and selecting the plurality of pixel disparities corresponding to the plurality of first end points and the plurality of second end points in the pixel disparity map.
6. The method of claim 1 , wherein the measuring of the visibility distance based on the plurality of pixel disparities comprises measuring the visibility distance further based on a baseline distance between the first camera and the second camera, and a focal length of the first camera and the second camera.
7. The method of claim 1 , wherein the extracting the plurality of first end points and the plurality of second end points comprises: estimating pixels corresponding to the plurality of first end points of the first image from the second image; and determining the pixels as the plurality of second end points of the second image.
8. The method of claim 1 , wherein the measuring of the visibility distance comprises: generating a vicinity distance map with respect to a vicinity of the vehicle using a light imaging, detection, and ranging (LiDAR) sensor; calibrating the vicinity distance map to the first image and the second image; and selecting a distance corresponding to the plurality of first end points and the plurality of second end points as the visibility distance, from the vicinity distance map.
9. The method of claim 1 , wherein the controlling of the velocity of the vehicle comprises: determining a stopping distance for the vehicle based on the visibility distance; calculating a maximum velocity of the vehicle based on the stopping distance; and adjusting the velocity of the vehicle to be less than or equal to the maximum velocity.
10. The method of claim 9 , wherein the calculating of the maximum velocity of the vehicle comprises calculating the maximum velocity of the vehicle further based on a length of the vehicle.
11. The method of claim 9 , further comprising: adjusting either one or both of the stopping distance and the maximum velocity in response to reception of a user input.
12. The method of claim 9 , wherein the calculating of the maximum velocity of the vehicle comprises: obtaining maximum velocity information corresponding to the location of the vehicle based on the location of the vehicle; and calculating the maximum velocity of the vehicle further based on the maximum velocity information.
13. The method of claim 9 , wherein the adjusting of the velocity of the vehicle comprises adjusting the velocity of the vehicle to be the maximum velocity in response to no object being detected.
14. The method of claim 1 , further comprising: determining a statistical value of distances between respective end point locations corresponding to the plurality of first end points and the plurality of second end points and the location of the vehicle to be the visibility distance.
15. The method of claim 1 , wherein the controlling of the velocity of the vehicle comprises: determining an obtainable stopping distance based on the visibility distance and a line shape of the road, and calculating a maximum velocity of the vehicle based on the obtainable stopping distance.
16. The method of claim 1 , wherein the controlling of the velocity of the vehicle comprises: excluding a reaction distance with respect to the vehicle; and determining a maximum velocity of the vehicle based on a braking distance.
17. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform the method of claim 1 .
18. An apparatus to control a velocity of a vehicle, the apparatus comprising: a first camera configured to acquire a first image of a road on which the vehicle travels; a second camera configured to acquire a second image of the road on which the vehicle travels; and a processor configured to: determine, from the first image, a first mad region of the road on which the vehicle is traveling; determine, from the second image, a second road region of the road on which the vehicle is traveling; extract a plurality of first end points of the first road region from the first image; extract a plurality of second end points of the second road region from the second image; determining a plurality of pixel disparities between the plurality of first end points and the plurality of second end points; measure a visibility distance between a position on the mad corresponding to the plurality of first end points and the plurality of second end points, and a location of the vehicle, based on the plurality of pixel disparities; and control the velocity of the vehicle based on the visibility distance.
19. The apparatus of claim 18 , wherein the processor is configured to extract the plurality of first end points and the plurality of second end points by determining a driving lane region from the first mad region and the second road region and extracting, as the plurality of first end points and the plurality of second end points, an end points of the driving lane region.
20. The apparatus of claim 18 , wherein the processor is configured to extract the plurality of first end points and the plurality of second end points by extracting, as the plurality of first end points and the plurality of second end points, pixels at farthest distances from a side of the vehicle in the first image and the second image, among pixels included in the first road region and the second road region.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
October 31, 2017
June 2, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.